Skip to main content
Glama

Prompt Auto-Optimizer MCP

by sloth-wq

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GEPA_DEFAULT_GENERATIONSNoDefault number of iterations10
GEPA_DEFAULT_POPULATION_SIZENoDefault number of prompt variants20
GEPA_MAX_CONCURRENT_PROCESSESNoParallel execution limit for performance tuning3

Schema

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Tools

Functions exposed to the LLM to take actions

NameDescription
gepa_start_evolution

Initialize evolution process with configuration and seed prompt

gepa_record_trajectory

Record execution trajectory for prompt evaluation

gepa_evaluate_prompt

Evaluate prompt candidate performance across multiple tasks

gepa_reflect

Analyze failures and generate prompt improvements

gepa_get_pareto_frontier

Retrieve optimal candidates from Pareto frontier

gepa_select_optimal

Select best prompt candidate for given context

gepa_create_backup

Create system backup including evolution state and trajectories

gepa_restore_backup

Restore system from a specific backup

gepa_list_backups

List available system backups

gepa_recovery_status

Get comprehensive disaster recovery status and health information

gepa_recover_component

Recover a specific GEPA component

gepa_integrity_check

Perform comprehensive data integrity check

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sloth-wq/prompt-auto-optimizer-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server